Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technology-related events and updates

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating partnership or conjunction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    grades
    -0.64
    Newsletter
    -0.64
    loss
    -0.62
    External
    -0.62
    ¢
    -0.61
     Airl
    -0.61
    zag
    -0.61
    âī
    -0.61
    onte
    -0.60
    ļéĨĴ
    -0.60
    POSITIVE LOGITS
     rightfully
    1.02
     hopefully
    1.00
     it
    0.95
     thankfully
    0.94
     luckily
    0.94
     congr
    0.89
     fortunately
    0.89
     unsurprisingly
    0.88
     judging
    0.88
     congratulations
    0.87
    Act Density 0.352%

    No Known Activations